001: /*
002: * Licensed to the Apache Software Foundation (ASF) under one or more
003: * contributor license agreements. See the NOTICE file distributed with
004: * this work for additional information regarding copyright ownership.
005: * The ASF licenses this file to You under the Apache License, Version 2.0
006: * (the "License"); you may not use this file except in compliance with
007: * the License. You may obtain a copy of the License at
008: *
009: * http://www.apache.org/licenses/LICENSE-2.0
010: *
011: * Unless required by applicable law or agreed to in writing, software
012: * distributed under the License is distributed on an "AS IS" BASIS,
013: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014: * See the License for the specific language governing permissions and
015: * limitations under the License.
016: */
017:
018: package org.apache.xerces.impl.xpath.regex;
019:
020: import java.util.Hashtable;
021: import java.util.Locale;
022:
023: /**
024: * A regular expression parser for the XML Schema.
025: *
026: * @xerces.internal
027: *
028: * @author TAMURA Kent <kent@trl.ibm.co.jp>
029: * @version $Id: ParserForXMLSchema.java 571468 2007-08-31 14:01:58Z knoaman $
030: */
031: class ParserForXMLSchema extends RegexParser {
032:
033: public ParserForXMLSchema() {
034: //this.setLocale(Locale.getDefault());
035: }
036:
037: public ParserForXMLSchema(Locale locale) {
038: //this.setLocale(locale);
039: }
040:
041: Token processCaret() throws ParseException {
042: this .next();
043: return Token.createChar('^');
044: }
045:
046: Token processDollar() throws ParseException {
047: this .next();
048: return Token.createChar('$');
049: }
050:
051: Token processLookahead() throws ParseException {
052: throw ex("parser.process.1", this .offset);
053: }
054:
055: Token processNegativelookahead() throws ParseException {
056: throw ex("parser.process.1", this .offset);
057: }
058:
059: Token processLookbehind() throws ParseException {
060: throw ex("parser.process.1", this .offset);
061: }
062:
063: Token processNegativelookbehind() throws ParseException {
064: throw ex("parser.process.1", this .offset);
065: }
066:
067: Token processBacksolidus_A() throws ParseException {
068: throw ex("parser.process.1", this .offset);
069: }
070:
071: Token processBacksolidus_Z() throws ParseException {
072: throw ex("parser.process.1", this .offset);
073: }
074:
075: Token processBacksolidus_z() throws ParseException {
076: throw ex("parser.process.1", this .offset);
077: }
078:
079: Token processBacksolidus_b() throws ParseException {
080: throw ex("parser.process.1", this .offset);
081: }
082:
083: Token processBacksolidus_B() throws ParseException {
084: throw ex("parser.process.1", this .offset);
085: }
086:
087: Token processBacksolidus_lt() throws ParseException {
088: throw ex("parser.process.1", this .offset);
089: }
090:
091: Token processBacksolidus_gt() throws ParseException {
092: throw ex("parser.process.1", this .offset);
093: }
094:
095: Token processStar(Token tok) throws ParseException {
096: this .next();
097: return Token.createClosure(tok);
098: }
099:
100: Token processPlus(Token tok) throws ParseException {
101: // X+ -> XX*
102: this .next();
103: return Token.createConcat(tok, Token.createClosure(tok));
104: }
105:
106: Token processQuestion(Token tok) throws ParseException {
107: // X? -> X|
108: this .next();
109: Token par = Token.createUnion();
110: par.addChild(tok);
111: par.addChild(Token.createEmpty());
112: return par;
113: }
114:
115: boolean checkQuestion(int off) {
116: return false;
117: }
118:
119: Token processParen() throws ParseException {
120: this .next();
121: Token tok = Token.createParen(this .parseRegex(), 0);
122: if (this .read() != T_RPAREN)
123: throw ex("parser.factor.1", this .offset - 1);
124: this .next(); // Skips ')'
125: return tok;
126: }
127:
128: Token processParen2() throws ParseException {
129: throw ex("parser.process.1", this .offset);
130: }
131:
132: Token processCondition() throws ParseException {
133: throw ex("parser.process.1", this .offset);
134: }
135:
136: Token processModifiers() throws ParseException {
137: throw ex("parser.process.1", this .offset);
138: }
139:
140: Token processIndependent() throws ParseException {
141: throw ex("parser.process.1", this .offset);
142: }
143:
144: Token processBacksolidus_c() throws ParseException {
145: this .next();
146: return this .getTokenForShorthand('c');
147: }
148:
149: Token processBacksolidus_C() throws ParseException {
150: this .next();
151: return this .getTokenForShorthand('C');
152: }
153:
154: Token processBacksolidus_i() throws ParseException {
155: this .next();
156: return this .getTokenForShorthand('i');
157: }
158:
159: Token processBacksolidus_I() throws ParseException {
160: this .next();
161: return this .getTokenForShorthand('I');
162: }
163:
164: Token processBacksolidus_g() throws ParseException {
165: throw this .ex("parser.process.1", this .offset - 2);
166: }
167:
168: Token processBacksolidus_X() throws ParseException {
169: throw ex("parser.process.1", this .offset - 2);
170: }
171:
172: Token processBackreference() throws ParseException {
173: throw ex("parser.process.1", this .offset - 4);
174: }
175:
176: int processCIinCharacterClass(RangeToken tok, int c) {
177: tok.mergeRanges(this .getTokenForShorthand(c));
178: return -1;
179: }
180:
181: /**
182: * Parses a character-class-expression, not a character-class-escape.
183: *
184: * c-c-expression ::= '[' c-group ']'
185: * c-group ::= positive-c-group | negative-c-group | c-c-subtraction
186: * positive-c-group ::= (c-range | c-c-escape)+
187: * negative-c-group ::= '^' positive-c-group
188: * c-c-subtraction ::= (positive-c-group | negative-c-group) subtraction
189: * subtraction ::= '-' c-c-expression
190: * c-range ::= single-range | from-to-range
191: * single-range ::= multi-c-escape | category-c-escape | block-c-escape | <any XML char>
192: * cc-normal-c ::= <any character except [, ], \>
193: * from-to-range ::= cc-normal-c '-' cc-normal-c
194: *
195: * @param useNrage Ignored.
196: * @return This returns no NrageToken.
197: */
198: protected RangeToken parseCharacterClass(boolean useNrange)
199: throws ParseException {
200: this .setContext(S_INBRACKETS);
201: this .next(); // '['
202: boolean nrange = false;
203: boolean wasDecoded = false; // used to detect if the last - was escaped.
204: RangeToken base = null;
205: RangeToken tok;
206: if (this .read() == T_CHAR && this .chardata == '^') {
207: nrange = true;
208: this .next(); // '^'
209: base = Token.createRange();
210: base.addRange(0, Token.UTF16_MAX);
211: tok = Token.createRange();
212: } else {
213: tok = Token.createRange();
214: }
215: int type;
216: boolean firstloop = true;
217: while ((type = this .read()) != T_EOF) { // Don't use 'cotinue' for this loop.
218:
219: wasDecoded = false;
220: // single-range | from-to-range | subtraction
221: if (type == T_CHAR && this .chardata == ']' && !firstloop) {
222: if (nrange) {
223: base.subtractRanges(tok);
224: tok = base;
225: }
226: break;
227: }
228: int c = this .chardata;
229: boolean end = false;
230: if (type == T_BACKSOLIDUS) {
231: switch (c) {
232: case 'd':
233: case 'D':
234: case 'w':
235: case 'W':
236: case 's':
237: case 'S':
238: tok.mergeRanges(this .getTokenForShorthand(c));
239: end = true;
240: break;
241:
242: case 'i':
243: case 'I':
244: case 'c':
245: case 'C':
246: c = this .processCIinCharacterClass(tok, c);
247: if (c < 0)
248: end = true;
249: break;
250:
251: case 'p':
252: case 'P':
253: int pstart = this .offset;
254: RangeToken tok2 = this .processBacksolidus_pP(c);
255: if (tok2 == null)
256: throw this .ex("parser.atom.5", pstart);
257: tok.mergeRanges(tok2);
258: end = true;
259: break;
260:
261: case '-':
262: c = this .decodeEscaped();
263: wasDecoded = true;
264: break;
265:
266: default:
267: c = this .decodeEscaped();
268: } // \ + c
269: } // backsolidus
270: else if (type == T_XMLSCHEMA_CC_SUBTRACTION && !firstloop) {
271: // Subraction
272: if (nrange) {
273: base.subtractRanges(tok);
274: tok = base;
275: }
276: RangeToken range2 = this .parseCharacterClass(false);
277: tok.subtractRanges(range2);
278: if (this .read() != T_CHAR || this .chardata != ']')
279: throw this .ex("parser.cc.5", this .offset);
280: break; // Exit this loop
281: }
282: this .next();
283: if (!end) { // if not shorthands...
284: if (type == T_CHAR) {
285: if (c == '[')
286: throw this .ex("parser.cc.6", this .offset - 2);
287: if (c == ']')
288: throw this .ex("parser.cc.7", this .offset - 2);
289: if (c == '-' && this .chardata != ']' && !firstloop)
290: throw this .ex("parser.cc.8", this .offset - 2); // if regex = '[-]' then invalid
291: }
292: if (this .read() != T_CHAR || this .chardata != '-'
293: || c == '-' && firstloop) { // Here is no '-'.
294: tok.addRange(c, c);
295: } else { // Found '-'
296: // Is this '-' is a from-to token??
297: this .next(); // Skips '-'
298: if ((type = this .read()) == T_EOF)
299: throw this .ex("parser.cc.2", this .offset);
300: // c '-' ']' -> '-' is a single-range.
301: if (type == T_CHAR && this .chardata == ']') { // if - is at the last position of the group
302: tok.addRange(c, c);
303: tok.addRange('-', '-');
304: } else if (type == T_XMLSCHEMA_CC_SUBTRACTION) {
305: throw this .ex("parser.cc.8", this .offset - 1);
306: } else {
307:
308: int rangeend = this .chardata;
309: if (type == T_CHAR) {
310: if (rangeend == '[')
311: throw this .ex("parser.cc.6",
312: this .offset - 1);
313: if (rangeend == ']')
314: throw this .ex("parser.cc.7",
315: this .offset - 1);
316: if (rangeend == '-')
317: throw this .ex("parser.cc.8",
318: this .offset - 2);
319: } else if (type == T_BACKSOLIDUS)
320: rangeend = this .decodeEscaped();
321: this .next();
322:
323: if (c > rangeend)
324: throw this .ex("parser.ope.3",
325: this .offset - 1);
326: tok.addRange(c, rangeend);
327: }
328: }
329: }
330: firstloop = false;
331: }
332: if (this .read() == T_EOF)
333: throw this .ex("parser.cc.2", this .offset);
334: tok.sortRanges();
335: tok.compactRanges();
336: //tok.dumpRanges();
337: this .setContext(S_NORMAL);
338: this .next(); // Skips ']'
339:
340: return tok;
341: }
342:
343: protected RangeToken parseSetOperations() throws ParseException {
344: throw this .ex("parser.process.1", this .offset);
345: }
346:
347: Token getTokenForShorthand(int ch) {
348: switch (ch) {
349: case 'd':
350: return ParserForXMLSchema.getRange("xml:isDigit", true);
351: case 'D':
352: return ParserForXMLSchema.getRange("xml:isDigit", false);
353: case 'w':
354: return ParserForXMLSchema.getRange("xml:isWord", true);
355: case 'W':
356: return ParserForXMLSchema.getRange("xml:isWord", false);
357: case 's':
358: return ParserForXMLSchema.getRange("xml:isSpace", true);
359: case 'S':
360: return ParserForXMLSchema.getRange("xml:isSpace", false);
361: case 'c':
362: return ParserForXMLSchema.getRange("xml:isNameChar", true);
363: case 'C':
364: return ParserForXMLSchema.getRange("xml:isNameChar", false);
365: case 'i':
366: return ParserForXMLSchema.getRange("xml:isInitialNameChar",
367: true);
368: case 'I':
369: return ParserForXMLSchema.getRange("xml:isInitialNameChar",
370: false);
371: default:
372: throw new RuntimeException(
373: "Internal Error: shorthands: \\u"
374: + Integer.toString(ch, 16));
375: }
376: }
377:
378: int decodeEscaped() throws ParseException {
379: if (this .read() != T_BACKSOLIDUS)
380: throw ex("parser.next.1", this .offset - 1);
381: int c = this .chardata;
382: switch (c) {
383: case 'n':
384: c = '\n';
385: break; // LINE FEED U+000A
386: case 'r':
387: c = '\r';
388: break; // CRRIAGE RETURN U+000D
389: case 't':
390: c = '\t';
391: break; // HORIZONTAL TABULATION U+0009
392: case '\\':
393: case '|':
394: case '.':
395: case '^':
396: case '-':
397: case '?':
398: case '*':
399: case '+':
400: case '{':
401: case '}':
402: case '(':
403: case ')':
404: case '[':
405: case ']':
406: break; // return actucal char
407: default:
408: throw ex("parser.process.1", this .offset - 2);
409: }
410: return c;
411: }
412:
413: static private Hashtable ranges = null;
414: static private Hashtable ranges2 = null;
415:
416: static synchronized protected RangeToken getRange(String name,
417: boolean positive) {
418: if (ranges == null) {
419: ranges = new Hashtable();
420: ranges2 = new Hashtable();
421:
422: Token tok = Token.createRange();
423: setupRange(tok, SPACES);
424: ranges.put("xml:isSpace", tok);
425: ranges2.put("xml:isSpace", Token.complementRanges(tok));
426:
427: tok = Token.createRange();
428: setupRange(tok, DIGITS);
429: ranges.put("xml:isDigit", tok);
430: ranges2.put("xml:isDigit", Token.complementRanges(tok));
431:
432: tok = Token.createRange();
433: setupRange(tok, DIGITS);
434: ranges.put("xml:isDigit", tok);
435: ranges2.put("xml:isDigit", Token.complementRanges(tok));
436:
437: tok = Token.createRange();
438: setupRange(tok, LETTERS);
439: tok.mergeRanges((Token) ranges.get("xml:isDigit"));
440: ranges.put("xml:isWord", tok);
441: ranges2.put("xml:isWord", Token.complementRanges(tok));
442:
443: tok = Token.createRange();
444: setupRange(tok, NAMECHARS);
445: ranges.put("xml:isNameChar", tok);
446: ranges2.put("xml:isNameChar", Token.complementRanges(tok));
447:
448: tok = Token.createRange();
449: setupRange(tok, LETTERS);
450: tok.addRange('_', '_');
451: tok.addRange(':', ':');
452: ranges.put("xml:isInitialNameChar", tok);
453: ranges2.put("xml:isInitialNameChar", Token
454: .complementRanges(tok));
455: }
456: RangeToken tok = positive ? (RangeToken) ranges.get(name)
457: : (RangeToken) ranges2.get(name);
458: return tok;
459: }
460:
461: static void setupRange(Token range, String src) {
462: int len = src.length();
463: for (int i = 0; i < len; i += 2)
464: range.addRange(src.charAt(i), src.charAt(i + 1));
465: }
466:
467: private static final String SPACES = "\t\n\r\r ";
468: private static final String NAMECHARS = "\u002d\u002e\u0030\u003a\u0041\u005a\u005f\u005f\u0061\u007a\u00b7\u00b7\u00c0\u00d6"
469: + "\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148\u014a\u017e\u0180\u01c3\u01cd\u01f0"
470: + "\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1\u02d0\u02d1\u0300\u0345\u0360\u0361"
471: + "\u0386\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da\u03dc\u03dc"
472: + "\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c\u045e\u0481"
473: + "\u0483\u0486\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
474: + "\u0531\u0556\u0559\u0559\u0561\u0586\u0591\u05a1\u05a3\u05b9\u05bb\u05bd\u05bf\u05bf"
475: + "\u05c1\u05c2\u05c4\u05c4\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0640\u0652\u0660\u0669"
476: + "\u0670\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06e8\u06ea\u06ed\u06f0\u06f9"
477: + "\u0901\u0903\u0905\u0939\u093c\u094d\u0951\u0954\u0958\u0963\u0966\u096f\u0981\u0983"
478: + "\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2\u09b6\u09b9\u09bc\u09bc"
479: + "\u09be\u09c4\u09c7\u09c8\u09cb\u09cd\u09d7\u09d7\u09dc\u09dd\u09df\u09e3\u09e6\u09f1"
480: + "\u0a02\u0a02\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36"
481: + "\u0a38\u0a39\u0a3c\u0a3c\u0a3e\u0a42\u0a47\u0a48\u0a4b\u0a4d\u0a59\u0a5c\u0a5e\u0a5e"
482: + "\u0a66\u0a74\u0a81\u0a83\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0"
483: + "\u0ab2\u0ab3\u0ab5\u0ab9\u0abc\u0ac5\u0ac7\u0ac9\u0acb\u0acd\u0ae0\u0ae0\u0ae6\u0aef"
484: + "\u0b01\u0b03\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33\u0b36\u0b39"
485: + "\u0b3c\u0b43\u0b47\u0b48\u0b4b\u0b4d\u0b56\u0b57\u0b5c\u0b5d\u0b5f\u0b61\u0b66\u0b6f"
486: + "\u0b82\u0b83\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f"
487: + "\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9\u0bbe\u0bc2\u0bc6\u0bc8\u0bca\u0bcd"
488: + "\u0bd7\u0bd7\u0be7\u0bef\u0c01\u0c03\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33"
489: + "\u0c35\u0c39\u0c3e\u0c44\u0c46\u0c48\u0c4a\u0c4d\u0c55\u0c56\u0c60\u0c61\u0c66\u0c6f"
490: + "\u0c82\u0c83\u0c85\u0c8c\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cbe\u0cc4"
491: + "\u0cc6\u0cc8\u0cca\u0ccd\u0cd5\u0cd6\u0cde\u0cde\u0ce0\u0ce1\u0ce6\u0cef\u0d02\u0d03"
492: + "\u0d05\u0d0c\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d3e\u0d43\u0d46\u0d48\u0d4a\u0d4d"
493: + "\u0d57\u0d57\u0d60\u0d61\u0d66\u0d6f\u0e01\u0e2e\u0e30\u0e3a\u0e40\u0e4e\u0e50\u0e59"
494: + "\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97\u0e99\u0e9f"
495: + "\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb9\u0ebb\u0ebd"
496: + "\u0ec0\u0ec4\u0ec6\u0ec6\u0ec8\u0ecd\u0ed0\u0ed9\u0f18\u0f19\u0f20\u0f29\u0f35\u0f35"
497: + "\u0f37\u0f37\u0f39\u0f39\u0f3e\u0f47\u0f49\u0f69\u0f71\u0f84\u0f86\u0f8b\u0f90\u0f95"
498: + "\u0f97\u0f97\u0f99\u0fad\u0fb1\u0fb7\u0fb9\u0fb9\u10a0\u10c5\u10d0\u10f6\u1100\u1100"
499: + "\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c\u113e\u113e"
500: + "\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159\u115f\u1161"
501: + "\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173\u1175\u1175"
502: + "\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba\u11bc\u11c2"
503: + "\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15\u1f18\u1f1d"
504: + "\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d\u1f5f\u1f7d"
505: + "\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3\u1fd6\u1fdb"
506: + "\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u20d0\u20dc\u20e1\u20e1\u2126\u2126\u212a\u212b"
507: + "\u212e\u212e\u2180\u2182\u3005\u3005\u3007\u3007\u3021\u302f\u3031\u3035\u3041\u3094"
508: + "\u3099\u309a\u309d\u309e\u30a1\u30fa\u30fc\u30fe\u3105\u312c\u4e00\u9fa5\uac00\ud7a3"
509: + "";
510: private static final String LETTERS = "\u0041\u005a\u0061\u007a\u00c0\u00d6\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148"
511: + "\u014a\u017e\u0180\u01c3\u01cd\u01f0\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1"
512: + "\u0386\u0386\u0388\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da"
513: + "\u03dc\u03dc\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c"
514: + "\u045e\u0481\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
515: + "\u0531\u0556\u0559\u0559\u0561\u0586\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0641\u064a"
516: + "\u0671\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06d5\u06e5\u06e6\u0905\u0939"
517: + "\u093d\u093d\u0958\u0961\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2"
518: + "\u09b6\u09b9\u09dc\u09dd\u09df\u09e1\u09f0\u09f1\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28"
519: + "\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36\u0a38\u0a39\u0a59\u0a5c\u0a5e\u0a5e\u0a72\u0a74"
520: + "\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0\u0ab2\u0ab3\u0ab5\u0ab9"
521: + "\u0abd\u0abd\u0ae0\u0ae0\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33"
522: + "\u0b36\u0b39\u0b3d\u0b3d\u0b5c\u0b5d\u0b5f\u0b61\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95"
523: + "\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9"
524: + "\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33\u0c35\u0c39\u0c60\u0c61\u0c85\u0c8c"
525: + "\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cde\u0cde\u0ce0\u0ce1\u0d05\u0d0c"
526: + "\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d60\u0d61\u0e01\u0e2e\u0e30\u0e30\u0e32\u0e33"
527: + "\u0e40\u0e45\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97"
528: + "\u0e99\u0e9f\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb0"
529: + "\u0eb2\u0eb3\u0ebd\u0ebd\u0ec0\u0ec4\u0f40\u0f47\u0f49\u0f69\u10a0\u10c5\u10d0\u10f6"
530: + "\u1100\u1100\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c"
531: + "\u113e\u113e\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159"
532: + "\u115f\u1161\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173"
533: + "\u1175\u1175\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba"
534: + "\u11bc\u11c2\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15"
535: + "\u1f18\u1f1d\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d"
536: + "\u1f5f\u1f7d\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3"
537: + "\u1fd6\u1fdb\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u2126\u2126\u212a\u212b\u212e\u212e"
538: + "\u2180\u2182\u3007\u3007\u3021\u3029\u3041\u3094\u30a1\u30fa\u3105\u312c\u4e00\u9fa5"
539: + "\uac00\ud7a3";
540: private static final String DIGITS = "\u0030\u0039\u0660\u0669\u06F0\u06F9\u0966\u096F\u09E6\u09EF\u0A66\u0A6F\u0AE6\u0AEF"
541: + "\u0B66\u0B6F\u0BE7\u0BEF\u0C66\u0C6F\u0CE6\u0CEF\u0D66\u0D6F\u0E50\u0E59\u0ED0\u0ED9"
542: + "\u0F20\u0F29";
543: }
|